{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 2120438.982076755, "end_time": 2121299.618132408, "total_evaluation_time_secondes": "860.6360556529835", "model_name": "HuggingFaceH4/zephyr-7b-gemma-sft-v0.1", "model_sha": "bfef69be8fbbd6a26fd570c337b4b829c24de736", "model_dtype": "torch.bfloat16", "model_size": "15.91 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2513863216266174, "prompt_level_strict_acc_stderr": 0.0186682161522404, "inst_level_strict_acc": 0.39568345323741005, "inst_level_strict_acc_stderr": 0.0004977713872112196, "prompt_level_loose_acc": 0.2532347504621072, "prompt_level_loose_acc_stderr": 0.01871357754365548, "inst_level_loose_acc": 0.40047961630695444, "inst_level_loose_acc_stderr": 0.0004927301213572242 } }, "versions": { "custom|ifeval|0": 0 }, "config_tasks": { "custom|ifeval": { "name": "ifeval", "prompt_function": "ifeval_prompt", "hf_repo": "wis-k/instruction-following-eval", "hf_subset": "default", "metric": [ "ifeval_metric" ], "hf_avail_splits": [ "train" ], "evaluation_splits": [ "train" ], "few_shots_split": "train", "few_shots_select": "random_sampling", "generation_size": 1280, "stop_sequence": [], "output_regex": null, "frozen": false, "suite": [ "custom" ], "original_num_docs": 541, "effective_num_docs": 541 } }, "summary_tasks": { "custom|ifeval|0": { "hashes": { "hash_examples": "e99cbf567588d7c6", "hash_full_prompts": "dffcf9a3b5dd7b3d", "hash_input_tokens": "697d713cee490081", "hash_cont_tokens": "297adba6668a5939" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "74abf332fe1a119c", "hash_input_tokens": "369e8568d4bc5b04", "hash_cont_tokens": "a971a9b624dc7e89" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }